Search Results for author:
Found 14 papers, 5 papers with code
Auxiliary Image Regularization for Deep CNNs with Noisy Labels
Precisely-labeled data sets with sufficient amount of samples are very important for training deep convolutional neural networks (CNNs).
Learning Detection with Diverse Proposals
To predict a set of diverse and informative proposals with enriched representations, this paper introduces a differentiable Determinantal Point Process (DPP) layer that is able to augment the object detection architectures.
Multi-Content GAN for Few-Shot Font Style Transfer
In this work, we focus on the challenge of taking partial observations of highly-stylized text and generalizing the observations to generate unobserved glyphs in the ornamented typeface.
Compositional GAN: Learning Image-Conditional Binary Composition
Generative Adversarial Networks (GANs) can produce images of remarkable complexity and realism but are generally structured to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could be present in a scene.
Discriminator Rejection Sampling
We propose a rejection sampling scheme using the discriminator of a GAN to approximately correct errors in the GAN generator distribution.
Compositional GAN (Extended Abstract): Learning Image-Conditional Binary Composition
Generative Adversarial Networks (GANs) can produce images of surprising complexity and realism but are generally structured to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could be present in a scene.
Semantic Bottleneck Scene Generation
For the former, we use an unconditional progressive segmentation generation network that captures the distribution of realistic semantic scene layouts.
Ranked #1 on
Image Generation
on Cityscapes-5K 256x512
Unconditional Synthesis of Complex Scenes Using a Semantic Bottleneck
Coupling the high-fidelity generation capabilities of label-conditional image synthesis methods with the flexibility of unconditional generative models, we propose a semantic bottleneck GAN model for unconditional synthesis of complex scenes.
More Control for Free! Image Synthesis with Semantic Diffusion Guidance
We investigate fine-grained, continuous control of this model class, and introduce a novel unified framework for semantic diffusion guidance, which allows either language or image guidance, or both.
Shape-Guided Diffusion with Inside-Outside Attention
We introduce precise object silhouette as a new form of user control in text-to-image diffusion models, which we dub Shape-Guided Diffusion.
Text-Conditional Contextualized Avatars For Zero-Shot Personalization
Recent large-scale text-to-image generation models have made significant improvements in the quality, realism, and diversity of the synthesized images and enable users to control the created content through language.
Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation
However, existing approaches are limited by their reliance on relatively small-scale motion capture data, leading to poor performance on more diverse, in-the-wild prompts.
Ranked #19 on
Motion Synthesis
on HumanML3D
Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning
We present Emu Video, a text-to-video generation model that factorizes the generation into two steps: first generating an image conditioned on the text, and then generating a video conditioned on the text and the generated image.
Motion-Conditioned Image Animation for Video Editing
We introduce MoCA, a Motion-Conditioned Image Animation approach for video editing.
